ScholarWorks@Dongguk University

Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

심층 신경망의 압축을 위한 입력 영상의 채널 감축 장치 및 그 방법APPARATUS AND METHOD FOR REDUCING THE NUMBER OF CHANNELS IN INPUT IMAGES TO COMPRESS DEEP NEURAL NETWORKS

Alternative Title
APPARATUS AND METHOD FOR REDUCING THE NUMBER OF CHANNELS IN INPUT IMAGES TO COMPRESS DEEP NEURAL NETWORKS
Authors
원치선; 정지수
URI
https://scholarworks.dongguk.edu/handle/sw.dongguk/60288
Abstract
본 발명은 정지영상 및 동영상을 위해 기 제안되고 훈련된 심층 신경망 (CNN) 구조를 압축하기 위해 영상을 재구성하여 상관성이 낮은 영상 채널을 통합하거나 삭제함으로써 입력 영상의 데이터량을 줄이고, 따라서 훈련시켜야 할 신경망의 필터 계수를 줄이는 방법에 관한 것이다.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > Department of Electronics and Electrical Engineering > 4. Patents
Show full item record

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

CONTACT US

RSS_1.0 RSS_2.0 ATOM_1.0

30, Pildong-ro 1-gil, Jung-gu, Seoul, 04620, Republic of Korea+82-2-2260-3114

Copyright(c) 2023 DONGGUK UNIVERSITY. ALL RIGHTS RESERVED.

Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.

BROWSE

한국어